Research
RDM: Recurrent Diffusion Model for Human Motion Generation
arXiv:2406.07169v3 Announce Type: replace Abstract: Human motion generation is a challenging task due to its high dimensionality and the difficulty of generating fine-grained motions. Diffusion method
arXiv:2406.07169v3 Announce Type: replace Abstract: Human motion generation is a challenging task due to its high dimensionality and the difficulty of generating fine-grained motions. Diffusion methods have been proposed due to their high sample quality and expressiveness. Early approaches treat the entire sequence as a whole, which is computationally expensive and restricts sequence length. In contrast, autoregressive diffusion models generate longer sequences. However, their reliance on fully denoising previous frames complicates training and inference. Consequently, we propose RDM, a new recurrent diffusion formulation inspired by Recurrent Neural Networks (RNNs). RDM explicitly conditions the diffusion process on preceding noisy frames, avoiding the cost of full denoising. To overcome the challenge of maintaining its probabilistic nature, we employ Normalizing Flows to model recurrent connections. Our evaluations demonstrate RDM's effectiveness: it achieves comparable performance to autoregressive baselines and generates long sequences that remain aligned with the text. RDM also skips diffusion steps during inference, reducing computational cost by up to 18x over autoregressive baselines. Project page: https://www.mirgahney.com/rfdm.io/.
Related
- AMD:Anatomical Motion Diffusion with Interpretable Motion Decomposition and Fusion
- BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis
- Towards Highly-Constrained Human Motion Generation with Retrieval-Guided Diffusion Noise Optimization
- Spatiotemporally Decoupled Autoregressive Diffusion Model for Human Motion Generation
- T2LM: Long-Term 3D Human Motion Generation from Multiple Sentences
Source: arXiv cs.CV | 2026-10-14